Skip to content

N
nltk
Commit a3206c11 by Long Thanh Duong
Options

Modify according to the recent changes in ParserI

parent cdcf6701
Showing with 69 additions and 20 deletions
nltk/parse/malt.py
......@@ -109,9 +109,9 @@ class MaltParser(ParserI):
:param sentence: Input sentence to parse
:type sentence: list(tuple(str, str))
:return: ``DependencyGraph`` the dependency graph representation of the sentence
:return: iter(DependencyGraph) the possible dependency graph representations of the sentence
"""
return self.tagged_parse_sents([sentence], verbose)[0]
return next(self.tagged_parse_sents([sentence], verbose))
def tagged_parse_sents(self, sentences, verbose=False):
"""
......@@ -156,7 +156,8 @@ class MaltParser(ParserI):
raise Exception("MaltParser parsing (%s) failed with exit "
"code %d" % (' '.join(cmd), ret))
return iter(DependencyGraph.load(output_file.name))
# Must return iter(iter(Tree))
return (iter([dep_graph]) for dep_graph in DependencyGraph.load(output_file.name))
finally:
input_file.close()
os.remove(input_file.name)
......@@ -241,6 +242,8 @@ def demo():
maltParser.parse_one(['John','sees','Mary'], verbose=verbose).tree().pprint()
maltParser.parse_one(['a','man','runs'], verbose=verbose).tree().pprint()
next(maltParser.tagged_parse([('John','NNP'),('sees','VB'),('Mary','NNP')], verbose)).tree().pprint()
if __name__ == '__main__':
demo()
nltk/parse/pchart.py
......@@ -397,10 +397,50 @@ def demo(choice=None, draw_parses=None, print_parses=None):
summary of the results are displayed.
"""
import sys, time
from nltk import tokenize, toy_pcfg1, toy_pcfg2
from nltk import tokenize
from nltk.parse import pchart
# Define two demos. Each demo has a sentence and a grammar.
toy_pcfg1 = PCFG.fromstring("""
S -> NP VP [1.0]
NP -> Det N [0.5] | NP PP [0.25] | 'John' [0.1] | 'I' [0.15]
Det -> 'the' [0.8] | 'my' [0.2]
N -> 'man' [0.5] | 'telescope' [0.5]
VP -> VP PP [0.1] | V NP [0.7] | V [0.2]
V -> 'ate' [0.35] | 'saw' [0.65]
PP -> P NP [1.0]
P -> 'with' [0.61] | 'under' [0.39]
""")
toy_pcfg2 = PCFG.fromstring("""
S -> NP VP [1.0]
VP -> V NP [.59]
VP -> V [.40]
VP -> VP PP [.01]
NP -> Det N [.41]
NP -> Name [.28]
NP -> NP PP [.31]
PP -> P NP [1.0]
V -> 'saw' [.21]
V -> 'ate' [.51]
V -> 'ran' [.28]
N -> 'boy' [.11]
N -> 'cookie' [.12]
N -> 'table' [.13]
N -> 'telescope' [.14]
N -> 'hill' [.5]
Name -> 'Jack' [.52]
Name -> 'Bob' [.48]
P -> 'with' [.61]
P -> 'under' [.39]
Det -> 'the' [.41]
Det -> 'a' [.31]
Det -> 'my' [.28]
""")
demos = [('I saw John with my telescope', toy_pcfg1),
('the boy saw Jack with Bob under the table with a telescope',
toy_pcfg2)]
......
nltk/parse/stanford.py
......@@ -29,10 +29,16 @@ class StanfordParser(ParserI):
>>> parser=StanfordParser(
... model_path="edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz"
... )
>>> parser.raw_parse_sents((
>>> list(parser.raw_parse("the quick brown fox jumps over the lazy dog"))
[Tree('ROOT', [Tree('NP', [Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['quick']), Tree('JJ', ['brown']),
Tree('NN', ['fox'])]), Tree('NP', [Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']),
Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])])])])]
>>> sum([list(dep_graphs) for dep_graphs in parser.raw_parse_sents((
... "the quick brown fox jumps over the lazy dog",
... "the quick grey wolf jumps over the lazy fox"
... ))
... ))], [])
[Tree('ROOT', [Tree('NP', [Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['quick']), Tree('JJ', ['brown']),
Tree('NN', ['fox'])]), Tree('NP', [Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']),
Tree('NP', [Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])])])]), Tree('ROOT', [Tree('NP',
......@@ -40,17 +46,17 @@ class StanfordParser(ParserI):
[Tree('NP', [Tree('NNS', ['jumps'])]), Tree('PP', [Tree('IN', ['over']), Tree('NP', [Tree('DT', ['the']),
Tree('JJ', ['lazy']), Tree('NN', ['fox'])])])])])])]
>>> parser.parse_sents((
>>> sum([list(dep_graphs) for dep_graphs in parser.parse_sents((
... "I 'm a dog".split(),
... "This is my friends ' cat ( the tabby )".split(),
... ))
... ))], [])
[Tree('ROOT', [Tree('S', [Tree('NP', [Tree('PRP', ['I'])]), Tree('VP', [Tree('VBP', ["'m"]),
Tree('NP', [Tree('DT', ['a']), Tree('NN', ['dog'])])])])]), Tree('ROOT', [Tree('S', [Tree('NP',
[Tree('DT', ['This'])]), Tree('VP', [Tree('VBZ', ['is']), Tree('NP', [Tree('NP', [Tree('NP', [Tree('PRP$', ['my']),
Tree('NNS', ['friends']), Tree('POS', ["'"])]), Tree('NN', ['cat'])]), Tree('PRN', [Tree('-LRB-', ['-LRB-']),
Tree('NP', [Tree('DT', ['the']), Tree('NN', ['tabby'])]), Tree('-RRB-', ['-RRB-'])])])])])])]
>>> parser.tagged_parse_sents((
>>> sum([list(dep_graphs) for dep_graphs in parser.tagged_parse_sents((
... (
... ("The", "DT"),
... ("quick", "JJ"),
......@@ -63,7 +69,7 @@ class StanfordParser(ParserI):
... ("dog", "NN"),
... (".", "."),
... ),
... ))
... ))],[])
[Tree('ROOT', [Tree('S', [Tree('NP', [Tree('DT', ['The']), Tree('JJ', ['quick']), Tree('JJ', ['brown']),
Tree('NN', ['fox'])]), Tree('VP', [Tree('VBD', ['jumped']), Tree('PP', [Tree('IN', ['over']), Tree('NP',
[Tree('DT', ['the']), Tree('JJ', ['lazy']), Tree('NN', ['dog'])])])]), Tree('.', ['.'])])])]
......@@ -103,11 +109,11 @@ class StanfordParser(ParserI):
cur_lines = []
for line in output_.splitlines(False):
if line == '':
res.append(Tree.fromstring('\n'.join(cur_lines)))
res.append(iter([Tree.fromstring('\n'.join(cur_lines))]))
cur_lines = []
else:
cur_lines.append(line)
return res
return iter(res)
def parse_sents(self, sentences, verbose=False):
"""
......@@ -120,7 +126,7 @@ class StanfordParser(ParserI):
:param sentences: Input sentences to parse
:type sentences: list(list(str))
:rtype: list(Tree)
:rtype: iter(iter(Tree))
"""
cmd = [
'edu.stanford.nlp.parser.lexparser.LexicalizedParser',
......@@ -141,9 +147,9 @@ class StanfordParser(ParserI):
:param sentence: Input sentence to parse
:type sentence: str
:rtype: Tree
:rtype: iter(Tree)
"""
return self.raw_parse_sents((sentence,), verbose)
return next(self.raw_parse_sents([sentence], verbose))
def raw_parse_sents(self, sentences, verbose=False):
"""
......@@ -153,7 +159,7 @@ class StanfordParser(ParserI):
:param sentences: Input sentences to parse
:type sentences: list(str)
:rtype: list(Tree)
:rtype: iter(iter(Tree))
"""
cmd = [
'edu.stanford.nlp.parser.lexparser.LexicalizedParser',
......@@ -171,9 +177,9 @@ class StanfordParser(ParserI):
:param sentence: Input sentence to parse
:type sentence: list(tuple(str, str))
:rtype: Tree
:rtype: iter(Tree)
"""
return self.tagged_parse_sents([sentence], verbose)[0]
return next(self.tagged_parse_sents([sentence], verbose))
def tagged_parse_sents(self, sentences, verbose=False):
"""
......@@ -183,7 +189,7 @@ class StanfordParser(ParserI):
:param sentences: Input sentences to parse
:type sentences: list(list(tuple(str, str)))
:rtype: Tree
:rtype: iter(iter(Tree))
"""
tag_separator = '/'
cmd = [
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment